摘要
研究了基于核主元分析的非线性系统故障检测问题.提出了一种改进的小波核主元分析的故障检测方法.该方法首先对数据进行小波去噪预处理,然后再利用小波核函数,将非线性的输入空间转换到线性特征空间.在特征空间使用主元分析,结合SPE统计量和T2统计量对非线性系统进行故障检测.仿真结果表明:该方法能够提高故障检测性能.
The problem of fault detection for a class of nonlinear systems based on kernel principal component analysis is studied. The improved wavelet kernel principal component analysis is proposed. Firstly,the proposed method is applied to denose the data. Then,the preprocessed data is transformed by wavelet kernel function to map the nonlinear input space into linear characterization space. In the feature space,principal component analysis is applied to detect faults for nonlinear system,in combination with SPE statistic and T2 statistic. Simulation results show that the method can improve the fault detection performance.
出处
《郑州大学学报（工学版）》
CAS
北大核心
2015年第1期97-100,共4页
Journal of Zhengzhou University（Engineering Science）
基金
国家自然科学基金资助项目(61471323)
河南省教育厅科学技术研究重点项目(14A120004)
关键词
核主元分析
小波核函数
小波去噪
故障检测
kernel principal component analysis
wavelet kernel function
wavelet denoising
fault detection
